面向少样本个性化实例识别的对象条件实例包
Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition
AI总结：
本文提出基于多阶统计量的对象条件实例包 OBoI，使通用目标检测模型无需反向传播即可在少样本条件下识别个人实例，并在 18 个实例上取得 77.1% 准确率，相对提升约 12%。
摘要：
如今，用户要求视觉系统具备更高的个性化能力，能够仅凭少样本数据集就定位和识别对象的个人实例（例如，识别“我的狗”而非“狗”这一类别）。尽管深度网络在传统的标签丰富基准上取得了出色成果（例如最新的 YOLOv8 模型在标准目标检测中的表现），但它们难以保持类内可变性，从而无法表示不同实例，而只能表示对象类别。我们构建了一种基于提取特征的多阶统计量的对象条件实例包（Object-conditioned Bag of Instances，OBoI），将通用目标检测模型扩展为能够从 OBoI 的度量空间中搜索和识别个人实例，而无需进行反向传播。通过依赖多阶统计量，OBoI 在区分不同实例方面取得了一致且优越的准确率。实验结果表明，在包含 18 个个人实例的情况下，我们实现了 77.1% 的个人对象识别准确率，相较于当前最先进方法取得了约 12% 的相对提升。
英文摘要：
Nowadays, users demand for increased personalization of vision systems to localize and identify personal instances of objects (e.g., my dog rather than dog) from a few-shot dataset only. Despite outstanding results of deep networks on classical label-abundant benchmarks (e.g., those of the latest YOLOv8 model for standard object detection), they struggle to maintain within-class variability to represent different instances rather than object categories only. We construct an Object-conditioned Bag of Instances (OBoI) based on multi-order statistics of extracted features, where generic object detection models are extended to search and identify personal instances from the OBoI's metric space, without need for backpropagation. By relying on multi-order statistics, OBoI achieves consistent superior accuracy in distinguishing different instances. In the results, we achieve 77.1% personal object recognition accuracy in case of 18 personal instances, showing about 12% relative gain over the state of the art.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
